Benchmark Almanac

Intern-S1-Pro

Intern-S1-Pro places in the top three on 2 benchmarks.

Shanghai AI Lab Released February 2nd, 2026 Family Intern-S1 The lab's model card Compare with others
22
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
Shanghai AI Lab Feb 2026

Intern-S1-Pro

Open weights Flagship

143.1 #152 of 404
Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.
  • MMMU-Pro 72.8% #49 /90
  • IFBench 71.2% #39 /80
  • Scientists' First Exam (SFE) 52.7% #3 /5

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
MMLU-Pro 86.6% #14 of 167 Lab model card
IFBench 71.2% #39 of 80 Lab model card

Math and science

BenchmarkScoreRankSource
AIME 2025 93.1% #33 of 143 Lab model card
IMO-AnswerBench 77.3% #30 of 37 Lab model card
Matbench 72.8 #2 of 2 Lab model card
SciReasoner evaluation suite 55.5% #2 of 2 Lab model card

Coding

BenchmarkScoreRankSource
LiveCodeBench v6 74.3% #46 of 90 Lab model card
SArena 83.5 #1 of 1 Lab model card

Agents and tools

BenchmarkScoreRankSource
ScreenSpot-v2 93.6% #4 of 14 Lab model card
tau2-bench 80.9% #32 of 79 Lab model card
GAIA 77.4% #3 of 5 Lab model card

Vision, audio and robotics

BenchmarkScoreRankSource
RefCOCO / RefCOCO+ / RefCOCOg 91.9% #8 of 29 Lab model card
MMMU-Pro 72.8% #49 of 90 Lab model card
Scientists' First Exam (SFE) 52.7% #3 of 5 Lab model card
OCRBench v2 60.1% #14 of 22 Lab model card
XLRS-Bench 52.8% #3 of 4 Lab model card
MicroVQA 63.3% #3 of 3 Lab model card
MSEarth 65.2% #2 of 2 Lab model card

Safety and security

BenchmarkScoreRankSource
LiveSecBench 63.6 #10 of 34 Official leaderboard
SMolInstruct 74.8% #1 of 2 Lab model card
Biology-Instructions 52.5% #2 of 2 Lab model card
Mol-Instructions 48.8% #2 of 2 Lab model card

Its lab's numbers put it at 143.1, number 152 of 404

The Self-Reported Index fits one score to the 10 capability results Shanghai AI Lab reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 140.2 to 146.0. How we compute it.

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Intern-S1-Pro model card (Hugging Face) Feb 2, 2026

Its system card

Every result in the longer documents the lab published with it. 1 of them isn't in the launch post.

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale Mar 26, 2026

Capabilities